| { | |
| "best_metric": 0.3231343924999237, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3062200956937799, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006124401913875598, | |
| "grad_norm": 1.1700061559677124, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2869, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006124401913875598, | |
| "eval_loss": 1.9100584983825684, | |
| "eval_runtime": 1.5044, | |
| "eval_samples_per_second": 33.236, | |
| "eval_steps_per_second": 8.641, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012248803827751197, | |
| "grad_norm": 1.2230859994888306, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2767, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018373205741626795, | |
| "grad_norm": 0.7630212903022766, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.2924, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024497607655502393, | |
| "grad_norm": 0.8332273364067078, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.2981, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03062200956937799, | |
| "grad_norm": 1.250927209854126, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.8525, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03674641148325359, | |
| "grad_norm": 1.4342719316482544, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.2618, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.042870813397129184, | |
| "grad_norm": 1.2296887636184692, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.2319, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.048995215311004786, | |
| "grad_norm": 1.5124156475067139, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.361, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05511961722488038, | |
| "grad_norm": 1.1411627531051636, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.1356, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06124401913875598, | |
| "grad_norm": 0.8585147261619568, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1643, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06736842105263158, | |
| "grad_norm": 0.8973323702812195, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.8697, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07349282296650718, | |
| "grad_norm": 0.6723853945732117, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.7553, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07961722488038278, | |
| "grad_norm": 0.44317373633384705, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.2797, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08574162679425837, | |
| "grad_norm": 0.33222272992134094, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.2048, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09186602870813397, | |
| "grad_norm": 0.17401014268398285, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1805, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09799043062200957, | |
| "grad_norm": 0.4258590340614319, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1634, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10411483253588517, | |
| "grad_norm": 0.4304857552051544, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.2866, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11023923444976076, | |
| "grad_norm": 1.197048306465149, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.8169, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 1.4760901927947998, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.9525, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12248803827751197, | |
| "grad_norm": 1.477898359298706, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.0918, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12861244019138757, | |
| "grad_norm": 1.0816622972488403, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.0453, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13473684210526315, | |
| "grad_norm": 1.4763364791870117, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.9559, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14086124401913874, | |
| "grad_norm": 1.3924659490585327, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.8979, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14698564593301436, | |
| "grad_norm": 0.9928950667381287, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.5703, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15311004784688995, | |
| "grad_norm": 1.1304906606674194, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.6697, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15311004784688995, | |
| "eval_loss": 0.4300152063369751, | |
| "eval_runtime": 1.4859, | |
| "eval_samples_per_second": 33.649, | |
| "eval_steps_per_second": 8.749, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15923444976076556, | |
| "grad_norm": 0.33280134201049805, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.2019, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16535885167464115, | |
| "grad_norm": 0.2794322669506073, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.1846, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17148325358851674, | |
| "grad_norm": 0.4203859567642212, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.1423, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.17760765550239235, | |
| "grad_norm": 0.5897067189216614, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.1647, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.18373205741626794, | |
| "grad_norm": 1.02996826171875, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.6039, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18985645933014353, | |
| "grad_norm": 2.1310155391693115, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.8006, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.19598086124401914, | |
| "grad_norm": 2.2415904998779297, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.8306, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20210526315789473, | |
| "grad_norm": 1.361811637878418, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.7494, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.20822966507177035, | |
| "grad_norm": 2.034090757369995, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.8148, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.21435406698564594, | |
| "grad_norm": 2.464292049407959, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.658, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22047846889952152, | |
| "grad_norm": 0.8960682153701782, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.5261, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.22660287081339714, | |
| "grad_norm": 0.8402606844902039, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.479, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": 0.34880414605140686, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.2051, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.23885167464114831, | |
| "grad_norm": 0.3065963387489319, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.1794, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.24497607655502393, | |
| "grad_norm": 0.2842368185520172, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.159, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25110047846889955, | |
| "grad_norm": 0.7232906818389893, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.1185, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.25722488038277513, | |
| "grad_norm": 0.6430230140686035, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.2502, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2633492822966507, | |
| "grad_norm": 1.1256890296936035, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.5465, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2694736842105263, | |
| "grad_norm": 1.3127527236938477, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.5744, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2755980861244019, | |
| "grad_norm": 1.1628435850143433, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6626, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2817224880382775, | |
| "grad_norm": 1.0411521196365356, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.5987, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.28784688995215313, | |
| "grad_norm": 1.2186107635498047, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.5531, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2939712918660287, | |
| "grad_norm": 0.935568630695343, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.5234, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3000956937799043, | |
| "grad_norm": 0.8467996716499329, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.3728, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3062200956937799, | |
| "grad_norm": 1.2814409732818604, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4109, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3062200956937799, | |
| "eval_loss": 0.3231343924999237, | |
| "eval_runtime": 1.522, | |
| "eval_samples_per_second": 32.851, | |
| "eval_steps_per_second": 8.541, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.589463780163584e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |